Datasets
Standard Dataset
Traffic Accident Detection Video Dataset for AI-Driven Computer Vision Systems in Smart City Transportation
- Citation Author(s):
-
VictorAdewopo
University of CincinnatiNellyElsayedUniversity of CincinnatiZagElSayedUniversity of CincinnatiMuratOzerUniversity of CincinnatiConstantinosZekiosFlorida International UniversityAhmedAbdelgawadCentral Michigan UniversityMagdyBayoumiUniversity of Louisiana - Submitted by:
- Victor Adewopo
- Last updated:
- Thu, 12/28/2023 - 15:13
- DOI:
- 10.21227/tjtg-nz28
- Data Format:
- Research Article Link:
- License:
1289 Views- Categories:
- Keywords:
Abstract
We introduce a novel dataset consisting of approximately 5,700 video files, specifically designed to enhance the development of real-time traffic accident detection systems in smart city environments. It encompasses a diverse range of traffic scenarios, captured through Traffic/Surveillance Cameras (Trafficam) and Dash Cameras (Dashcam), along with additional external data sources. The dataset is meticulously organized into three segments: Training, Validation, and Testing, with each segment offering a unique blend of traffic and dashcam footage across different scenarios.
The dataset is divided into eight classes: Backend, Backend Rollover, Frontend, Frontend Rollover, No Accident Normal Traffic, Sidehit, Sidehit Rollover, and General Augmented Crash. These classes provide a rich tapestry of real-world situations, ranging from routine traffic conditions to complex accident scenes. The distribution of the dataset is as follows: 3,912 files for Training, 1,054 for Validation, and 725 for Testing, encompassing a mix of accident and normal traffic scenarios from both Trafficam and Dashcam sources, along with additional external data.
The videos have been processed and segmented into five (5) seconds non-overlapping clips to ensure conciseness, focusing on the rapid dynamics of accidents. This careful curation and classification make the dataset an invaluable resource for training and evaluating AI models in traffic safety applications. By providing a wide array of scenarios, this dataset enables researchers and developers to develop state-of-the-art algorithms, ensuring high accuracy and reliability in diverse urban settings. This dataset is crucial for academic research and also serves as a practical tool for improving traffic management and safety in smart cities, contributing significantly to the collaborative efforts in creating safer, more efficient urban environments.
This dataset is tailored for training and evaluating AI models in traffic accident detection within smart city environments. It comprises a collection of zipped files containing MP4 video files, captured from Traffic/Surveillance Cameras and Dash Cameras, and categorized into various classes of traffic scenarios.
Dataset Structure
The dataset is organized into three primary directories: Training, Validation, and Testing. Each directory contains zipped files for different classes of traffic scenarios, ensuring a structured and organized approach to data management.
Traffic_Accident_Detection_Dataset/
├── Training/
│ ├── Backend.zip
│ ├── Backend_Rollover.zip
│ ├── Frontend.zip
│ ├── Frontend_Rollover.zip
│ ├── No_Accident_Normal_Traffic.zip
│ ├── Sidehit.zip
│ ├── Sidehit_Rollover.zip
│ └── General_Augmented_Crash.zip
├── Validation/
│ ├── Backend.zip
│ ├── Backend_Rollover.zip
│ ├── Frontend.zip
│ ├── Frontend_Rollover.zip
│ ├── No_Accident_Normal_Traffic.zip
│ ├── Sidehit.zip
│ ├── Sidehit_Rollover.zip
│ └── General_Augmented_Crash.zip
└── Testing/
├── Backend.zip
├── Backend_Rollover.zip
├── Frontend.zip
├── Frontend_Rollover.zip
├── No_Accident_Normal_Traffic.zip
├── Sidehit.zip
├── Sidehit_Rollover.zip
└── General_Augmented_Crash.zip
File Types:
ZIP: Each ZIP file contains MP4 video files representing different traffic scenarios within the respective category.
Instructions for Use
Download and Extract:
Extract the contents of each ZIP file to your preferred location.
Explore the Dataset:
Navigate through the Training, Validation, and Testing directories.
Each category of traffic scenarios is contained within its own ZIP file.
Utilize the Data:
Extract the MP4 files from the ZIP archives for model training, validation, and testing.
These video files are crucial for training and evaluating your models accurately in recognizing and classifying different types of traffic scenarios.
Model Training and Evaluation:
Use the extracted video files from the Training directory for model training.
Employ the Validation data to fine-tune and validate your model's performance.
Test the overall performance of your model using the extracted video files from the Testing data.
Feedback and Contribution:
Users are encouraged to provide feedback on the dataset usage and share their findings.
Contributions to enhance the dataset, such as additional annotations or new video scenarios, are welcome.
Additional Notes
Ensure that you have the necessary software to unzip and handle large video files.
Respect privacy and ethical considerations when using and sharing.
Citation References
This dataset has been utilized in the following research papers. If you use this dataset in your research, you may cite any of the following papers:
- Adewopo, V., & Elsayed, N. (2023). Smart City Transportation: Deep Learning Ensemble Approach for Traffic Accident Detection. arXiv preprint arXiv:2310.10038.
- Victor Adewopo, Nelly Elsayed, Zag ElSayed, Murat Ozer, Constantinos Zekios, Ahmed Abdelgawad, Magdy Bayoumi. (2023). Traffic Accident Detection Video Dataset for AI-Driven Computer Vision Systems in Smart City Transportation. IEEE Dataport. https://dx.doi.org/10.21227/tjtg-nz28
- Adewopo, V., Elsayed, N., ElSayed, Z., Ozer, M., Wangia-Anderson, V., & Abdelgawad, A. (2023, November). AI on the Road: A Comprehensive Analysis of Traffic Accidents and Autonomous Accident Detection System in Smart Cities. In 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI) (pp. 501-506). IEEE.
- Adewopo, V. A., Elsayed, N., ElSayed, Z., Ozer, M., Abdelgawad, A., & Bayoumi, M. (2023). A review on action recognition for accident detection in smart city transportation systems. Journal of Electrical Systems and Information Technology, 10(1), 57.
